diff --git a/configs/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb.py b/configs/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb.py
index 75273502f4..e8539d2410 100644
--- a/configs/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb.py
+++ b/configs/recognition/r2plus1d/r2plus1d_r34_32x2x1_180e_kinetics400_rgb.py
@@ -105,7 +105,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 180
 checkpoint_config = dict(interval=5)
 evaluation = dict(
diff --git a/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py b/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py
index f364860bb9..a7acbc484c 100644
--- a/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py
+++ b/configs/recognition/r2plus1d/r2plus1d_r34_8x8x1_180e_kinetics400_rgb.py
@@ -105,7 +105,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 180
 checkpoint_config = dict(interval=5)
 evaluation = dict(
diff --git a/configs/recognition/r2plus1d/r2plus1d_r34_video_8x8x1_180e_kinetics400_rgb.py b/configs/recognition/r2plus1d/r2plus1d_r34_video_8x8x1_180e_kinetics400_rgb.py
index 33e812c2ee..402bb45a18 100644
--- a/configs/recognition/r2plus1d/r2plus1d_r34_video_8x8x1_180e_kinetics400_rgb.py
+++ b/configs/recognition/r2plus1d/r2plus1d_r34_video_8x8x1_180e_kinetics400_rgb.py
@@ -116,7 +116,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 180
 checkpoint_config = dict(interval=5)
 evaluation = dict(
diff --git a/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py b/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py
index 3cb74e0701..67e52010a0 100644
--- a/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowfast/slowfast_r50_4x16x1_256e_kinetics400_rgb.py
@@ -111,7 +111,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 256
 checkpoint_config = dict(interval=4)
 workflow = [('train', 1)]
diff --git a/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py b/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py
index 18a9ab08bf..63b0a5250c 100644
--- a/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowfast/slowfast_r50_8x8x1_256e_kinetics400_rgb.py
@@ -111,7 +111,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 256
 checkpoint_config = dict(interval=4)
 workflow = [('train', 1)]
diff --git a/configs/recognition/slowfast/slowfast_r50_video_4x16x1_256e_kinetics400_rgb.py b/configs/recognition/slowfast/slowfast_r50_video_4x16x1_256e_kinetics400_rgb.py
index 708ce05e52..283bbbdaf4 100644
--- a/configs/recognition/slowfast/slowfast_r50_video_4x16x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowfast/slowfast_r50_video_4x16x1_256e_kinetics400_rgb.py
@@ -121,7 +121,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 256
 checkpoint_config = dict(interval=4)
 workflow = [('train', 1)]
diff --git a/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py b/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py
index 86ee95c165..c7a1e9bdd6 100644
--- a/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py
+++ b/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_flow.py
@@ -102,7 +102,7 @@
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
 lr_config = dict(
-    policy='CosineAnealing',
+    policy='CosineAnnealing',
     min_lr=0,
     warmup='linear',
     warmup_by_epoch=True,
diff --git a/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py b/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py
index 37fd24fc79..6980bcebf5 100644
--- a/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowonly/slowonly_r50_4x16x1_256e_kinetics400_rgb.py
@@ -94,7 +94,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 256
 checkpoint_config = dict(interval=4)
 workflow = [('train', 1)]
diff --git a/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow.py b/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow.py
index 93199932b1..2c1424b576 100644
--- a/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow.py
+++ b/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_flow.py
@@ -102,7 +102,7 @@
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
 lr_config = dict(
-    policy='CosineAnealing',
+    policy='CosineAnnealing',
     min_lr=0,
     warmup='linear',
     warmup_by_epoch=True,
diff --git a/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py b/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py
index 284c34fd74..2477bb22a9 100644
--- a/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowonly/slowonly_r50_8x8x1_256e_kinetics400_rgb.py
@@ -94,7 +94,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 256
 checkpoint_config = dict(interval=4)
 workflow = [('train', 1)]
diff --git a/configs/recognition/slowonly/slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py b/configs/recognition/slowonly/slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py
index 1127017c09..fbe7f44fc8 100644
--- a/configs/recognition/slowonly/slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py
+++ b/configs/recognition/slowonly/slowonly_r50_video_4x16x1_256e_kinetics400_rgb.py
@@ -104,7 +104,7 @@
     weight_decay=0.0001)  # this lr is used for 8 gpus
 optimizer_config = dict(grad_clip=dict(max_norm=40, norm_type=2))
 # learning policy
-lr_config = dict(policy='CosineAnealing', min_lr=0)
+lr_config = dict(policy='CosineAnnealing', min_lr=0)
 total_epochs = 256
 checkpoint_config = dict(interval=4)
 workflow = [('train', 1)]
diff --git a/docs/config.md b/docs/config.md
index 7be1ed374c..4d79362ded 100644
--- a/docs/config.md
+++ b/docs/config.md
@@ -158,7 +158,7 @@ optimizer_config = dict(  # Config used to build the optimizer hook
     grad_clip=None)  # Most of the methods do not use gradient clip
 # learning policy
 lr_config = dict(  # Learning rate scheduler config used to register LrUpdater hook
-    policy='step',  # Policy of scheduler, also support CosineAnealing, Cyclic, etc. Refer to details of supported LrUpdater from https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/lr_updater.py#L9
+    policy='step',  # Policy of scheduler, also support CosineAnnealing, Cyclic, etc. Refer to details of supported LrUpdater from https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/lr_updater.py#L9
     step=7)  # Steps to decay the learning rate
 
 total_epochs = 9  # Total epochs to train the model
@@ -364,7 +364,7 @@ optimizer_config = dict(  # Config used to build the optimizer hook
     grad_clip=dict(max_norm=40, norm_type=2))  # Use gradient clip
 # learning policy
 lr_config = dict(  # Learning rate scheduler config used to register LrUpdater hook
-    policy='step',  # Policy of scheduler, also support CosineAnealing, Cyclic, etc. Refer to details of supported LrUpdater from https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/lr_updater.py#L9
+    policy='step',  # Policy of scheduler, also support CosineAnnealing, Cyclic, etc. Refer to details of supported LrUpdater from https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/lr_updater.py#L9
     step=[40, 80])  # Steps to decay the learning rate
 total_epochs = 100  # Total epochs to train the model
 checkpoint_config = dict(  # Config to set the checkpoint hook, Refer to https://github.com/open-mmlab/mmcv/blob/master/mmcv/runner/hooks/checkpoint.py for implementation